{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:SSF5QFAOE7CRFV7IU7L2ZI34YH","short_pith_number":"pith:SSF5QFAO","schema_version":"1.0","canonical_sha256":"948bd8140e27c512d7e8a7d7aca37cc1e3cacce48497146ec52f1123b4f67ba9","source":{"kind":"arxiv","id":"2508.17435","version":1},"attestation_state":"computed","paper":{"title":"An LLM-LVLM Driven Agent for Iterative and Fine-Grained Image Editing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Haoran Ma, Jiahao Sun, Zihan Liang","submitted_at":"2025-08-24T16:28:18Z","abstract_excerpt":"Despite the remarkable capabilities of text-to-image (T2I) generation models, real-world applications often demand fine-grained, iterative image editing that existing methods struggle to provide. Key challenges include granular instruction understanding, robust context preservation during modifications, and the lack of intelligent feedback mechanisms for iterative refinement. This paper introduces RefineEdit-Agent, a novel, training-free intelligent agent framework designed to address these limitations by enabling complex, iterative, and context-aware image editing. RefineEdit-Agent leverages "},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2508.17435","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-08-24T16:28:18Z","cross_cats_sorted":[],"title_canon_sha256":"30e7216d7134627bc25bdafb86d660101ece98908267510311428d70f298d095","abstract_canon_sha256":"8b6765ddcc34020a809e83ecbdb99461549bd8400be7f55932a0004c3a74eaf3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:58:41.414254Z","signature_b64":"PkN8b/K7B9wzMcoY2wTTF8YBGL2pUeVFIqA2cgEEF/HO2EYv8A+qfXSKP1gMwEWlUQc4c0ZDXqT6ySRJSx01Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"948bd8140e27c512d7e8a7d7aca37cc1e3cacce48497146ec52f1123b4f67ba9","last_reissued_at":"2026-07-05T11:58:41.413736Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:58:41.413736Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"An LLM-LVLM Driven Agent for Iterative and Fine-Grained Image Editing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Haoran Ma, Jiahao Sun, Zihan Liang","submitted_at":"2025-08-24T16:28:18Z","abstract_excerpt":"Despite the remarkable capabilities of text-to-image (T2I) generation models, real-world applications often demand fine-grained, iterative image editing that existing methods struggle to provide. Key challenges include granular instruction understanding, robust context preservation during modifications, and the lack of intelligent feedback mechanisms for iterative refinement. This paper introduces RefineEdit-Agent, a novel, training-free intelligent agent framework designed to address these limitations by enabling complex, iterative, and context-aware image editing. RefineEdit-Agent leverages "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.17435","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2508.17435/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2508.17435","created_at":"2026-07-05T11:58:41.413804+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.17435v1","created_at":"2026-07-05T11:58:41.413804+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.17435","created_at":"2026-07-05T11:58:41.413804+00:00"},{"alias_kind":"pith_short_12","alias_value":"SSF5QFAOE7CR","created_at":"2026-07-05T11:58:41.413804+00:00"},{"alias_kind":"pith_short_16","alias_value":"SSF5QFAOE7CRFV7I","created_at":"2026-07-05T11:58:41.413804+00:00"},{"alias_kind":"pith_short_8","alias_value":"SSF5QFAO","created_at":"2026-07-05T11:58:41.413804+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.07051","citing_title":"Making Implicit Preservation Intent Explicit in Conversational Image Editing","ref_index":47,"is_internal_anchor":true},{"citing_arxiv_id":"2605.30248","citing_title":"GenClaw: Code-Driven Agentic Image Generation","ref_index":37,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SSF5QFAOE7CRFV7IU7L2ZI34YH","json":"https://pith.science/pith/SSF5QFAOE7CRFV7IU7L2ZI34YH.json","graph_json":"https://pith.science/api/pith-number/SSF5QFAOE7CRFV7IU7L2ZI34YH/graph.json","events_json":"https://pith.science/api/pith-number/SSF5QFAOE7CRFV7IU7L2ZI34YH/events.json","paper":"https://pith.science/paper/SSF5QFAO"},"agent_actions":{"view_html":"https://pith.science/pith/SSF5QFAOE7CRFV7IU7L2ZI34YH","download_json":"https://pith.science/pith/SSF5QFAOE7CRFV7IU7L2ZI34YH.json","view_paper":"https://pith.science/paper/SSF5QFAO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.17435&json=true","fetch_graph":"https://pith.science/api/pith-number/SSF5QFAOE7CRFV7IU7L2ZI34YH/graph.json","fetch_events":"https://pith.science/api/pith-number/SSF5QFAOE7CRFV7IU7L2ZI34YH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SSF5QFAOE7CRFV7IU7L2ZI34YH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SSF5QFAOE7CRFV7IU7L2ZI34YH/action/storage_attestation","attest_author":"https://pith.science/pith/SSF5QFAOE7CRFV7IU7L2ZI34YH/action/author_attestation","sign_citation":"https://pith.science/pith/SSF5QFAOE7CRFV7IU7L2ZI34YH/action/citation_signature","submit_replication":"https://pith.science/pith/SSF5QFAOE7CRFV7IU7L2ZI34YH/action/replication_record"}},"created_at":"2026-07-05T11:58:41.413804+00:00","updated_at":"2026-07-05T11:58:41.413804+00:00"}